paper-with-me

Papers

Robust normalizing flows using Bernstein-type polynomials

2021-02-06 · Sameera Ramasinghe, Kasun Fernando, Salman Khan, Nick Barnes

Modeling real-world distributions can often be challenging due to sample data that are subjected to perturbations, e.g., instrumentation errors, or added random noise. Since flow models are typically nonlinear algorithms, they amplify these initial errors, leading to poor generalizations. This paper proposes a framework to construct Normalizing Flows (NF), which demonstrates higher robustness against such initial errors. To this end, we utilize Bernstein-type polynomials inspired by the optimal stability of the Bernstein basis. Further, compared to the existing NF frameworks, our method provides compelling advantages like theoretical upper bounds for the approximation error, higher interpretability, suitability for compactly supported densities, and the ability to employ higher degree polynomials without training instability. We conduct a thorough theoretical analysis and empirically demonstrate the efficacy of the proposed technique using experiments on both real-world and synthetic datasets.

📄 PDF Abstract BibTeX arXiv:2102.03509

Code (0)

등록된 구현이 없습니다.

Tasks

Vocal Bursts Type Prediction

Methods 이 논문이 사용한 방법론

Normalizing Flows Normalizing Flows are a method for constructing complex distributions by transforming a probability density through a series of invertible mappings. By repeatedly applying…

Similar Papers 제목 키워드 기반

Universal Learning of Stochastic Dynamics for Exact Belief Propagation using Bernstein Normalizing Flows

2025-09-19 · Peter Amorese, Morteza Lahijanian arxiv

Predicting the distribution of future states in a stochastic system, known as belief propagation, is fundamental to reasoning under uncertainty. However, nonlinear dynamics often make analytical belief propagation intrac…

Density Estimation

Bernstein Flows for Flexible Posteriors in Variational Bayes

2022-02-11 · Oliver Dürr, Stephan Hörling, Daniel Dold, Ivonne Kovylov 외

Variational inference (VI) is a technique to approximate difficult to compute posteriors by optimization. In contrast to MCMC, VI scales to many observations. In the case of complex posteriors, however, state-of-the-art …

Variational Inference

Short-Term Density Forecasting of Low-Voltage Load using Bernstein-Polynomial Normalizing Flows

2022-04-29 · Marcel Arpogaus, Marcus Voss, Beate Sick, Mark Nigge-Uricher 외

The transition to a fully renewable energy grid requires better forecasting of demand at the low-voltage level to increase efficiency and ensure reliable control. However, high fluctuations and increasing electrification…

Decision MakingLoad ForecastingProbabilistic Deep LearningProbabilistic Time Series Forecasting

Gray level image enhancement using the Bernstein polynomials

2014-12-18 · Vasile Patrascu

This paper presents a method for enhancing the gray level images. This presented method takes part from the category of point operations and it is based on piecewise linear functions. The interpolation nodes of these fun…

Image Enhancement

ReachNN: Reachability Analysis of Neural-Network Controlled Systems

2019-06-25 · Chao Huang, Jiameng Fan, Wenchao Li, Xin Chen 외

Applying neural networks as controllers in dynamical systems has shown great promises. However, it is critical yet challenging to verify the safety of such control systems with neural-network controllers in the loop. Pre…